English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Fraud detection is a challenging task due to the changing nature of fraudpatterns over time and the limited availability of fraud examples to learn suchsophisticated patterns. Thus, fraud detection with the aid of smart versions ofmachine learning (ML) tools is essential to assure safety. Fraud detection is aprimary ML classification task; however, the optimum performance of thecorresponding ML tool relies on the usage of the best hyperparameter values.Moreover, classification under imbalanced classes is quite challenging as itcauses poor performance in minority classes, which most ML classificationtechniques ignore. Thus, we investigate four state-of-the-art ML techniques,namely, logistic regression, decision trees, random forest, and extremegradient boost, that are suitable for handling imbalance classes to maximizeprecision and simultaneously reduce false positives. First, these classifiersare trained on two original benchmark unbalanced fraud detection datasets,namely, phishing website URLs and fraudulent credit card transactions. Then,three synthetically balanced datasets are produced for each original data setby implementing the sampling frameworks, namely, RandomUnderSampler, SMOTE, andSMOTEENN. The optimum hyperparameters for all the 16 experiments are revealedusing the method RandomzedSearchCV. The validity of the 16 approaches in thecontext of fraud detection is compared using two benchmark performance metrics,namely, area under the curve of receiver operating characteristics (AUC ROC)and area under the curve of precision and recall (AUC PR). For both phishingwebsite URLs and credit card fraud transaction datasets, the results indicatethat extreme gradient boost trained on the original data shows trustworthyperformance in the imbalanced dataset and manages to outperform the other threemethods in terms of both AUC ROC and AUC PR.

Fraud Detection Using Optimized Machine Learning Tools Under Imbalance Classes